© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 371
    Prev
    Next
    INDEX
    Explanations

    the verb "write" and related terms, even if misspelled or hyphenated

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.72
    IBOutlet
    -0.58
    RelativeTo
    -0.54
    favicon
    -0.54
     AppCompatTheme
    -0.54
    ReusableCell
    -0.53
    noinspection
    -0.52
     MainAxisSize
    -0.51
    BoxShadow
    -0.51
     GBIF
    -0.51
    POSITIVE LOGITS
     writers
    1.02
     writer
    0.96
     writing
    0.96
     written
    0.95
     write
    0.94
     books
    0.93
     text
    0.91
     manuscripts
    0.89
    write
    0.88
     texts
    0.87
    Activations Density 1.341%

    No Known Activations